基于C3NET和图滤波器的基因特征选择算法

Gene feature selection algorithm based on C3NET and graph filter

针对基因表达数据维度高,冗余基因多等问题,提出了一种基于C3NET和图滤波器的基因特征选择算法。利用C3NET算法推断出基因表达数据的基因调控网络,得到基因之间的调控关系。将基因表达数据中的基因建模为图上节点,每个基因的基因数据建模为图信号,将得到的基因调控网络建模为邻接矩阵,计算该基因调控网络的图拉普拉斯矩阵和图傅里叶变换,并且提出了一种基于图傅里叶变换的基因分类能力的评估方法,计算每个基因的分类能力。设计了高通图滤波器对基因数据进行滤波,根据计算得到的基因的分类能力,筛选出滤波后分类能力高的基因。仿真实验结果表明,与现有的基因选择算法相比,本算法筛选出的基因分类能力更高,在不同的分类器中均能保持较高的分类准确率。

In this paper,a gene feature selection algorithm based on C3NET and graph filter is proposed to solve the problem that there are multiple redundant genes in high dimensional gene expression data.Firstly,the gene regulation network of gene expression data was deduced by C3NET algorithm to obtain the regulatory relationship between genes.Secondly,for the gene expression data,the genes were modeled as nodes on the graph and the gene data of each gene was modeled as graph signals.The obtained gene regulation network was modeled as adjacency matrix.Then,the graph Laplacian matrix and the graph Fourier transform of the gene regulation network were calculated.Moreover,an evaluation method of gene classification ability based on graph Fourier transform was proposed to calculate the classification ability of each gene.Finally,a high-pass filter was designed to filter the gene data,and the genes with high classification ability were screened out according to the calculated classification ability of the genes.The simulation results show that compared with the existing gene selection algorithms,the classification ability of the proposed algorithm is higher than that of comparison algorithms and the proposed algorithm can maintain high classification accuracy in different classifiers.